Emulation of expensive simulation model for operation and maintenance of offshore wind farms

Jayanta Majumder, Iraklis Lazakis, Yalcin Dalgic, Iain Dinwoodie, Matthew Revie, David McMillan

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

As wind farms move deeper offshore to tap into stronger and relentless winds, intense wind and wave conditions pose a great challenge in terms of their operation and maintenance (O&M). There are several factors that determine the profitability of offshore wind farms, and the most critical factors among them are the parameters on allocation of maintenance resources. These parameters interact with environmental factors and make it impossible to estimate profitability using simple formulas. On the other hand, existing simulation models, which describe the behaviour of wind farms by using mathematical models of wind, wave, and their effects on O&M, can be extremely detailed resulting in simulations being computationally very expensive. Depending on the number of scenarios to evaluate, it can take up-to several days to complete the computation. In order to address this difficulty, a statistical model fitting approach has been adopted to emulate the behaviour of the computationally expensive simulator. Neural networks, splines, and decision trees are combined to capture numerical and discrete variables and their influence on availability and profitability. This approach is useful because it allows for quick exploration of the space of operating choices, which would be difficult to achieve by repeated simulations due to their computational expense. The performance results show that the statistical model can evaluate hundreds of scenarios per second, and the approximation error is acceptable.
LanguageEnglish
Title of host publicationState of the Art on Energy Developments
Subtitle of host publicationProceedings of the 8th International Conference on Sustainable Energy & Environmental Protection
Place of PublicationPaisley
Publication statusPublished - 11 Aug 2015
Event8th International Conference on Sustainable Energy & Environmental Protection (SEEP 2015) - http://www.seepconference.co.uk/, Glasgow, United Kingdom
Duration: 11 Aug 201514 Aug 2015

Conference

Conference8th International Conference on Sustainable Energy & Environmental Protection (SEEP 2015)
CountryUnited Kingdom
CityGlasgow
Period11/08/1514/08/15

Fingerprint

Offshore wind farms
Profitability
Decision trees
Splines
Simulators
Farm
Simulation model
Emulation
Availability
Mathematical models
Neural networks

Keywords

  • statistical Models
  • neural networks
  • decision trees
  • splines
  • offshore wind farms
  • operation and maintenance

Cite this

Majumder, J., Lazakis, I., Dalgic, Y., Dinwoodie, I., Revie, M., & McMillan, D. (2015). Emulation of expensive simulation model for operation and maintenance of offshore wind farms. In State of the Art on Energy Developments: Proceedings of the 8th International Conference on Sustainable Energy & Environmental Protection Paisley.
Majumder, Jayanta ; Lazakis, Iraklis ; Dalgic, Yalcin ; Dinwoodie, Iain ; Revie, Matthew ; McMillan, David. / Emulation of expensive simulation model for operation and maintenance of offshore wind farms. State of the Art on Energy Developments: Proceedings of the 8th International Conference on Sustainable Energy & Environmental Protection. Paisley, 2015.
@inproceedings{171347c6e3134894882690533ff2276c,
title = "Emulation of expensive simulation model for operation and maintenance of offshore wind farms",
abstract = "As wind farms move deeper offshore to tap into stronger and relentless winds, intense wind and wave conditions pose a great challenge in terms of their operation and maintenance (O&M). There are several factors that determine the profitability of offshore wind farms, and the most critical factors among them are the parameters on allocation of maintenance resources. These parameters interact with environmental factors and make it impossible to estimate profitability using simple formulas. On the other hand, existing simulation models, which describe the behaviour of wind farms by using mathematical models of wind, wave, and their effects on O&M, can be extremely detailed resulting in simulations being computationally very expensive. Depending on the number of scenarios to evaluate, it can take up-to several days to complete the computation. In order to address this difficulty, a statistical model fitting approach has been adopted to emulate the behaviour of the computationally expensive simulator. Neural networks, splines, and decision trees are combined to capture numerical and discrete variables and their influence on availability and profitability. This approach is useful because it allows for quick exploration of the space of operating choices, which would be difficult to achieve by repeated simulations due to their computational expense. The performance results show that the statistical model can evaluate hundreds of scenarios per second, and the approximation error is acceptable.",
keywords = "statistical Models, neural networks, decision trees, splines, offshore wind farms, operation and maintenance",
author = "Jayanta Majumder and Iraklis Lazakis and Yalcin Dalgic and Iain Dinwoodie and Matthew Revie and David McMillan",
year = "2015",
month = "8",
day = "11",
language = "English",
isbn = "9781903978528",
booktitle = "State of the Art on Energy Developments",

}

Majumder, J, Lazakis, I, Dalgic, Y, Dinwoodie, I, Revie, M & McMillan, D 2015, Emulation of expensive simulation model for operation and maintenance of offshore wind farms. in State of the Art on Energy Developments: Proceedings of the 8th International Conference on Sustainable Energy & Environmental Protection. Paisley, 8th International Conference on Sustainable Energy & Environmental Protection (SEEP 2015), Glasgow, United Kingdom, 11/08/15.

Emulation of expensive simulation model for operation and maintenance of offshore wind farms. / Majumder, Jayanta; Lazakis, Iraklis; Dalgic, Yalcin; Dinwoodie, Iain; Revie, Matthew; McMillan, David.

State of the Art on Energy Developments: Proceedings of the 8th International Conference on Sustainable Energy & Environmental Protection. Paisley, 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Emulation of expensive simulation model for operation and maintenance of offshore wind farms

AU - Majumder, Jayanta

AU - Lazakis, Iraklis

AU - Dalgic, Yalcin

AU - Dinwoodie, Iain

AU - Revie, Matthew

AU - McMillan, David

PY - 2015/8/11

Y1 - 2015/8/11

N2 - As wind farms move deeper offshore to tap into stronger and relentless winds, intense wind and wave conditions pose a great challenge in terms of their operation and maintenance (O&M). There are several factors that determine the profitability of offshore wind farms, and the most critical factors among them are the parameters on allocation of maintenance resources. These parameters interact with environmental factors and make it impossible to estimate profitability using simple formulas. On the other hand, existing simulation models, which describe the behaviour of wind farms by using mathematical models of wind, wave, and their effects on O&M, can be extremely detailed resulting in simulations being computationally very expensive. Depending on the number of scenarios to evaluate, it can take up-to several days to complete the computation. In order to address this difficulty, a statistical model fitting approach has been adopted to emulate the behaviour of the computationally expensive simulator. Neural networks, splines, and decision trees are combined to capture numerical and discrete variables and their influence on availability and profitability. This approach is useful because it allows for quick exploration of the space of operating choices, which would be difficult to achieve by repeated simulations due to their computational expense. The performance results show that the statistical model can evaluate hundreds of scenarios per second, and the approximation error is acceptable.

AB - As wind farms move deeper offshore to tap into stronger and relentless winds, intense wind and wave conditions pose a great challenge in terms of their operation and maintenance (O&M). There are several factors that determine the profitability of offshore wind farms, and the most critical factors among them are the parameters on allocation of maintenance resources. These parameters interact with environmental factors and make it impossible to estimate profitability using simple formulas. On the other hand, existing simulation models, which describe the behaviour of wind farms by using mathematical models of wind, wave, and their effects on O&M, can be extremely detailed resulting in simulations being computationally very expensive. Depending on the number of scenarios to evaluate, it can take up-to several days to complete the computation. In order to address this difficulty, a statistical model fitting approach has been adopted to emulate the behaviour of the computationally expensive simulator. Neural networks, splines, and decision trees are combined to capture numerical and discrete variables and their influence on availability and profitability. This approach is useful because it allows for quick exploration of the space of operating choices, which would be difficult to achieve by repeated simulations due to their computational expense. The performance results show that the statistical model can evaluate hundreds of scenarios per second, and the approximation error is acceptable.

KW - statistical Models

KW - neural networks

KW - decision trees

KW - splines

KW - offshore wind farms

KW - operation and maintenance

UR - http://esdac.jrc.ec.europa.eu/event/8th-international-conference-sustainable-energy-environmental-protection-seep-2015

M3 - Conference contribution book

SN - 9781903978528

BT - State of the Art on Energy Developments

CY - Paisley

ER -

Majumder J, Lazakis I, Dalgic Y, Dinwoodie I, Revie M, McMillan D. Emulation of expensive simulation model for operation and maintenance of offshore wind farms. In State of the Art on Energy Developments: Proceedings of the 8th International Conference on Sustainable Energy & Environmental Protection. Paisley. 2015